Search NASA⌕ Search

SEARCH · Search NASA

Results for “asynchronous algorithms”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

167-PFlops Deep Learning for Electron Microscopy: From Learning Physics to Atomic Manipulation

An artificial intelligence system called MENNDL, which used 25,200 Nvidia Volta GPUs on Oak Ridge National Laboratory’s Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity toward nanofabricating materials automatically. Finally, MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

97 MATHEMATICS AND COMPUTING↗

167-PFlops deep learning for electron microscopy: from learning physics to atomic manipulation

An artificial intelligence system called MENNDL, which used 25,200 NVIDIA Volta GPUs on Oak Ridge National Laboratory's Summit machine, automatically designed an optimal deep learning network in order to extract structural information from raw atomic-resolution microscopy data. In a few hours, MENNDL creates and evaluates millions of networks using a scalable, parallel, asynchronous genetic algorithm augmented with a support vector machine to automatically find a superior deep learning network topology and hyper-parameter set than a human expert can find in months. For the application of electron microscopy, the system furthers the goal of improving our understanding of the electron-beam-matter interactions and real-time image-based feedback, which enables a huge step beyond human capacity towards nanofabricating materials automatically. MENNDL has been scaled to the 4,200 available nodes of Summit achieving a measured 152.5 PFlops, with an estimated sustained performance of 167 PFlops when the entire machine is available.

Patton, Robert↗

A First-Passage Kinetic Monte Carlo algorithm for complex diffusion-reaction systems

We develop an asynchronous event-driven First-Passage Kinetic Monte Carlo (FPKMC) algorithm for continuous time and space systems involving multiple diffusing and reacting species of spherical particles in two and three dimensions. The FPKMC algorithm presented here is based on the method introduced in Oppelstrup et al. and is implemented in a robust and flexible framework. Unlike standard KMC algorithms such as the n-fold algorithm, FPKMC is most efficient at low densities where it replaces the many small hops needed for reactants to find each other with large first-passage hops sampled from exact time-dependent Green's functions, without sacrificing accuracy. We describe in detail the key components of the algorithm, including the event-loop and the sampling of first-passage probability distributions, and demonstrate the accuracy of the new method. We apply the FPKMC algorithm to the challenging problem of simulation of long-term irradiation of metals, relevant to the performance and aging of nuclear materials in current and future nuclear power plants. The problem of radiation damage spans many decades of time-scales, from picosecond spikes caused by primary cascades, to years of slow damage annealing and microstructure evolution. Our implementation of the FPKMC algorithm has been able to simulate the irradiation of a metal sample for durations that are orders of magnitude longer than any previous simulations using the standard Object KMC or more recent asynchronous algorithms.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Asynchronous distributed-memory task-parallel algorithm for compressible flows on unstructured 3D Eulerian grids

Here, we discuss the implementation of a finite element method, used to numerically solve the Euler equations of compressible flows, using an asynchronous runtime system (RTS). The algorithm is implemented for distributed-memory machines, using stationary unstructured 3D meshes, combining data-, and task-parallelism on top of the Charm++ RTS. Charm++’s execution model is asynchronous by default, allowing arbitrary overlap of computation and communication. Task-parallelism allows scheduling parts of an algorithm independently of, or dependent on, each other. Built-in automatic load balancing enables continuous redistribution of computational load by migration of work units based on real-time CPU load measurement. The RTS also features automatic checkpointing, fault tolerance, resilience against hardware failure, and supports power-, and energy-aware computation. We demonstrate scalability up to 25 x 10 9 cells at $\mathscr{O}$10 4 compute cores and the benefits of automatic load balancing for irregular workloads. The full source code with documentation is available at https://quinoacomputing.org.

42 ENGINEERING↗

Scenario Decomposition for 0-1 Stochastic Programs: Improvements and Asynchronous Implementation

We recently proposed scenario decomposition algorithm for stochastic 0-1 programs finds an optimal solution by evaluating and removing individual solutions that are discovered by solving scenario subproblems. In our work, we develop an asynchronous, distributed implementation of the algorithm which has computational advantages over existing synchronous implementations of the algorithm. Improvements to both the synchronous and asynchronous algorithm are proposed. We also test the results on well known stochastic 0-1 programs from the SIPLIB test library and is able to solve one previously unsolved instance from the test set.

97 MATHEMATICS AND COMPUTING↗

Frog: Asynchronous Graph Processing on GPU with Hybrid Coloring Model

GPUs have been increasingly used to accelerate graph processing for complicated computational problems regarding graph theory. Many parallel graph algorithms adopt the asynchronous computing model to accelerate the iterative convergence. Unfortunately, the consistent asynchronous computing requires locking or atomic operations, leading to significant penalties/overheads when implemented on GPUs. As such, coloring algorithm is adopted to separate the vertices with potential updating conflicts, guaranteeing the consistency/correctness of the parallel processing. Common coloring algorithms, however, may suffer from low parallelism because of a large number of colors generally required for processing a large-scale graph with billions of vertices. We propose a light-weight asynchronous processing framework called Frog with a preprocessing/hybrid coloring model. The fundamental idea is based on Pareto principle (or 80-20 rule) about coloring algorithms as we observed through masses of realworld graph coloring cases. We find that a majority of vertices (about 80%) are colored with only a few colors, such that they can be read and updated in a very high degree of parallelism without violating the sequential consistency. Accordingly, our solution separates the processing of the vertices based on the distribution of colors. In this work, we mainly answer three questions: (1) how to partition the vertices in a sparse graph with maximized parallelism, (2) how to process large-scale graphs that cannot fit into GPU memory, and (3) how to reduce the overhead of data transfers on PCIe while processing each partition. Here, we conduct experiments on real-world data (Amazon, DBLP, YouTube, RoadNet-CA, WikiTalk and Twitter) to evaluate our approach and make comparisons with well-known non-preprocessed (such as Totem, Medusa, MapGraph and Gunrock) and preprocessed (Cusha) approaches, by testing four classical algorithms (BFS, PageRank, SSSP and CC). On all the tested applications and datasets, Frog is able to significantly outperform existing GPU-based graph processing systems except Gunrock and MapGraph. MapGraph gets better performance than Frog when running BFS on RoadNet-CA. The comparison between Gunrock and Frog is inconclusive. Frog can outperform Gunrock more than 1.04X when running PageRank and SSSP, while the advantage of Frog is not obvious when running BFS and CC on some datasets especially for RoadNet-CA.

97 MATHEMATICS AND COMPUTING↗

GVT Algorithms and Discrete Event Dynamics on 128K+ Processor Cores

Parallel discrete event simulation (PDES) represents a class of codes that are challenging to scale to large number of processors due to tight global timestamp-ordering and fine-grained event execution. One of the critical factors in scaling PDES is the efficiency of the underlying global virtual time (GVT) algorithm needed for correctness of parallel execution and speed of progress. Although many GVT algorithms have been proposed previously, few have been proposed for scalable asynchronous execution and none customized to exploit one-sided communication. Moreover, the detailed performance effects of actual GVT algorithm implementations on large platforms are unknown. Here, three major GVT algorithms intended for scalable execution on high-performance systems are studied: (1) a synchronous GVT algorithm that affords ease of implementation, (2) an asynchronous GVT algorithm that is more complex to implement but can relieve blocking latencies, and (3) a variant of the asynchronous GVT algorithm, proposed and studied for the first time here, to exploit one-sided communication in extant supercomputing platforms. Performance results are presented of implementations of these algorithms on over 64,000 cores of a Cray XT5 system, exercised on a range of parameters: optimistic and conservative synchronization, fine- to medium-grained event computation, synthetic and non-synthetic applications, and different lookahead values. Performance of tens of billions of events executed per second are registered, exceeding the speeds of any known PDES engine, and showing asynchronous GVT algorithms to outperform state-of-the-art synchronous GVT algorithms. Detailed PDES-specific runtime metrics are presented to further the understanding of tightly-coupled discrete event execution dynamics on massively parallel platforms.

99 GENERAL AND MISCELLANEOUS↗

Asynchronous and Load-Balanced Union-Find for Distributed and Parallel Scientific Data Visualization and Analysis

We present a novel distributed union-find algorithm that features asynchronous parallelism and k-d tree based load balancing for scalable visualization and analysis of scientific data. Applications of union-find include level set extraction and critical point tracking, but distributed union-find can suffer from high synchronization costs and imbalanced workloads across parallel processes. In this study, we prove that global synchronizations in existing distributed union-find can be eliminated without changing final results, allowing overlapped communications and computations for scalable processing. We also use a k-d tree decomposition to redistribute inputs, in order to improve workload balancing. We benchmark the scalability of our algorithm with up to 1,024 processes using both synthetic and application data. Here, we demonstrate the use of our algorithm in critical point tracking and super-level set extraction with high-speed imaging experiments and fusion plasma simulations, respectively.

97 MATHEMATICS AND COMPUTING↗

A communication-avoiding 3D algorithm for sparse LU factorization on heterogeneous systems

We propose a new algorithm to improve the strong scalability of right-looking sparse LU factorization on distributed memory systems. Our 3D algorithm for sparse LU uses a three-dimensional MPI process grid, exploits elimination tree parallelism, and trades off increased memory for reduced per-process communication. We also analyze the asymptotic improvements for planar graphs (e.g., those arising from 2D grid or mesh discretizations) and certain non-planar graphs (specifically for 3D grids and meshes). For a planar graph with $n$ vertices, our algorithm reduces communication volume asymptotically in $n$ by a factor of $\mathscr{O}$ $\Big(\sqrt{log \ n}\Big)$ and latency by a factor of $\mathscr{O}$ $(log \ n)$. For nonplanar cases, our algorithm can reduce the per-process communication volume by 3× and latency by $\mathscr{O}$ $\Big(n^\frac13\Big)$ times. In all cases, the memory needed to achieve these gains is a constant factor. We implemented our algorithm by extending the 2D data structure used in SuperLU_DIST. Our new 3D code achieves empirical speedups up to 27× for planar graphs and up to 3.3× for non-planar graphs over the baseline 2D SuperLU_DIST when run on 24,000 cores of a Cray XC30. We extend the 3D algorithm for heterogeneous architectures by adding the Highly Asynchronous Lazy Offload (Halo) algorithm for co-processor offload. On 4096 nodes of a Cray XK7 with 32,768 CPU cores and 4096 Nvidia K20x GPUs, the 3D algorithm achieves empirical speedups up to 24× for planar graphs and 3.5× for non-planar graphs over the baseline 2D SuperLU_DIST with co-processor acceleration.

97 MATHEMATICS AND COMPUTING↗

A Synchronization-Avoiding Distance-1 Grundy Coloring Algorithm for Power-Law Graphs

In this paper, we propose a distributed, unordered, label-correcting distance-1 Grundy (vertex) coloring algorithm, namely, Distributed Control (DC) coloring algorithm. Our algorithm eliminates the need for vertex-centric barriers and global synchronization for color refinement, relying only on atomic operations and local termination detection to update vertex color. DC proceeds optimistically, correcting the colors asynchronously as the algorithm progresses and depends on local ordering of tasks to minimize the execution of sub-optimal work. We implement our DC coloring algorithm and the well-known Jones-Plassmann algorithm and compare their performance with 4 different types of standard RMAT graphs and real-world graphs. We show that the elimination of waiting time of global and vertex-centric barriers and investing this time for local ordering leads to improved scaling for graphs with prominent power-law characteristics and densely interconnected local subgraphs.

Firoz, Jesun S.↗

Synchronous and asynchronous optimized Schwarz methods for one-way subdivision of bounded domains

Convergence of both synchronous and asynchronous optimized Schwarz algorithms for the shifted Laplacian operator on a bounded rectangular domain, in a one-way subdivision of the computational domain, with overlap, is shown. Convergence results are obtained under very mild conditions on the size of the subdomains and on the amount of overlap. A couple of results are also given, relating the convergence rate of the asynchronous method to changes in the size of the domain. Numerical experiments illustrate the theoretical results.

97 MATHEMATICS AND COMPUTING↗

Asynchronously parallel optimization solver for finding multiple minima

This paper proposes and analyzes an asynchronously parallel optimization algorithm for finding multiple, high-quality minima of nonlinear optimization problems. Our multistart algorithm considers all previously evaluated points when determining where to start or continue a local optimization run. Theoretical results show that, under certain assumptions, the algorithm almost surely starts a finite number of local optimization runs and identifies, or has a single local optimization run converging to, every minimum. The algorithm is applicable to general optimization settings, but our numerical results focus on the case when derivatives are unavailable. In numerical tests, a PYTHON implementation of the algorithm is shown to yield good approximations of many minima (including a global minimum), and this ability scales well with additional resources. Our implementation’s time to solution is shown also to scale well even when the time to evaluate the function evaluation is highly variable.

97 MATHEMATICS AND COMPUTING↗

Quinoa, Version 0.1

Quinoa is a set of computational tools that enables research and numerical analysis in fluid dynamics. At this time it is a test-bed to experiment with various algorithms using fully asynchronous runtime systems.

Bakosi, Jozsef↗

Quinoa, Version 0.1

Quinoa is a set of computational tools that enables research and numerical analysis in fluid dynamics. At this time it is a test-bed to experiment with various algorithms using fully asynchronous runtime systems.

Bakosi, Jozsef↗

Automating Discovery of Physics-Informed Neural State Space Models via Learning and Evolution

Recent works exploring deep learning application to dynamical systems modeling have demonstrated that embedding physical priors into neural networks can yield more effective, physically-realistic, and data-efficient models. However, in the absence of complete prior knowledge of a dynamical system's physical characteristics, determining the optimal structure and optimization strategy for these models can be difficult. In this work, we explore methods for discovering neural state space dynamics models for system identification. Starting with a design space of block-oriented state space models and structured linear maps with strong physical priors, we encode these components into a model genome alongside network structure, penalty constraints, and optimization hyperparameters. Demonstrating the overall utility of the design space, we employ an asynchronous genetic search algorithm that alternates between model selection and optimization and obtains accurate physically consistent models of three physical systems: an aerodynamics body, a continuous stirred tank reactor, and a two tank interacting system.

genetic algorithms, neural architecture search, ne↗

Power Minimization techniques for Networked Data Centers.

Our objective is to develop a mathematical model to optimize energy consumption at multiple levels in networked data centers, and develop abstract algorithms to optimize not only individual servers, but also coordinate the energy consumption of clusters of servers within a data center and across geographically distributed data centers to minimize the overall energy cost and consumption of brown energy of an enterprise. In this project, we have formulated a variety of optimization models, some stochastic others deterministic, and have obtained a variety of qualitative results on the structural properties, robustness, and scalability of the optimal policies. We have also systematically derived from these models decentralized algorithms to optimize energy efficiency, analyzed their optimality and stability properties. Finally, we have conducted preliminary numerical simulations to illustrate the behavior of these algorithms. We draw the following conclusion. First, there is a substantial opportunity to minimize both the amount and the cost of electricity consumption in a network of datacenters, by exploiting the fact that traffic load, electricity cost, and availability of renewable generation fluctuate over time and across geographical locations. Judiciously matching these stochastic processes can optimize the tradeoff between brown energy consumption, electricity cost, and response time. Second, given the stochastic nature of these three processes, real-time dynamic feedback should form the core of any optimization strategy. The key is to develop decentralized algorithms that can be implemented at different parts of the network as simple, local algorithms that coordinate through asynchronous message passing.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Modifying the Asynchronous Jacobi Method for Data Corruption Resilience

Moving scientific computation from high-performance computing (HPC) and cloud computing (CC) environments to devices on the edge, i.e., physically near instruments of interest, has received tremendous interest in recent years. Such edge computing environments can operate on data in situ, offering enticing benefits over data aggregation to HPC and CC facilities that include avoiding costs of transmission, increased data privacy, and real-time data analysis. Because of the inherent unreliability of edge computing environments, new fault-tolerant approaches must be developed before the benefits of edge computing can be realized. Motivated by algorithm-based fault tolerance, a variant of the asynchronous Jacobi (ASJ) method is developed that achieves resilience to data corruption by rejecting solution approximations from neighbor devices according to a bound derived from convergence theory. Numerical results on a two-dimensional Poisson problem show that the new rejection criterion, along with a novel approximation to the shortest path length on which the criterion depends, restores convergence for the ASJ variant in the presence of certain types data corruption. Numerical results are obtained for when the singular values in the analytic bound are approximated. Additional linear systems are also explored, one with a more dense sparsity pattern and one that includes advection. All results indicate that successful resilience to data corruption depends on whether the bound tightens fast enough to reject corrupted data before the iteration evolution deviates significantly from that predicted by the convergence theory defining the bound. This observation generalizes to future work on algorithm-based fault tolerance for other asynchronous algorithms, including upcoming approaches that leverage Krylov subspaces.

97 MATHEMATICS AND COMPUTING↗

Adaptive Runtime Features For Distributed Graph Algorithms

Performance of distributed graph algorithms can benefit greatly by forming rapport between algorithmic abstraction and the underlying runtime system that is responsible for scheduling work and exchanging messages. However, due to their dynamic and irregular nature of computation, distributed graph algorithms written in different programming models impose varying degree of workload pressure on the runtime. To cope with such vastly different workload characteristics, a runtime has to make several trade-offs. One such trade-off arises, for example, when the runtime scheduler has to choose among alternatives such as whether to execute algorithmic work, or progress the network by probing network buffers, or throttle sending messages (termed flow control). This tradeoff decides between optimizing the throughput of a runtime scheduler by increasing the rate of execution of algorithmic work, and reducing the latency of the network messages. Another trade-off exists when a decision has to be made about when to send aggregated messages in buffers (message coalescing). This decision chooses between trading off latency for network bandwidth and vice versa. At any instant, such trade-offs emphasize either on improving the quantity of work being executed (by maximizing the scheduler throughput) or on improving the quality of work (by prioritizing better work). However, encoding static policies for different runtime features (such as flow control, coalescing) can prevent graph algorithms from achieving their full potential, thus can undermine the actual performance of a distributed graph algorithm . In this paper, we investigate runtime support for distributed graph algorithms in the context of two paradigms: variants of wellknown Bulk-Synchronous Parallel model and asynchronous programming model. We explore generic runtime features such as message coalescing (aggregation) and flow control and show that execution policies of these features need to be adjusted over time to make a positive impact on the execution time of a distributed graph algorithm. Since synchronous and asynchronous graph algorithms have different workload characteristics, not all of such runtime features may be good candidates for adaptation. Each of these algorithmic paradigms may require different set of features to be adapted over time. We demonstrate which set of feature(s) can be useful in each case to achieve the right balance of work in the runtime layer. Existing implementation of different graph algorithms can benefit from adapting dynamic policies in the underlying runtime.

Firoz, Jesun S.↗